Multi-View Attributed Graph Clustering

doi:10.1109/TKDE.2021.3101227

Multi-View Attributed Graph Clustering

2021-01-01

120

PRE

AI

DOI：10.1109/TKDE.2021.3101227

Original

Original request for help

Save

Abstract

En 中文

Multi-view graph clustering has been intensively investigated during the past years. However, existing methods are still limited in two main aspects. On the one hand, most of them can not deal with data that have both attributes and graphs. Nowadays, multi-view attributed graph data are ubiquitous and the need for effective clustering methods is growing. On the other hand, many state-of-the-art algorithms are either shallow or deep models. Shallow methods may seriously restrict their capacity for modeling complex data, while deep approaches often involve large number of parameters and are expensive to train in terms of running time and space needed. In this paper, we propose a novel multi-view attributed graph clustering (MAGC) framework, which exploits both node attributes and graphs. Our novelty lies in three aspects. First, instead of deep neural networks, we apply a graph filtering technique to achieve a smooth node representation. Second, the original graph could be noisy or incomplete and is not directly applicable, thus we learn a consensus graph from data by considering the heterogeneous views. Third, high-order relations are explored in a flexible way by designing a new regularizer. Extensive experiments demonstrate the superiority of our method in terms of effectiveness and efficiency.

Keywords:

Clustering methods

Sparse matrices

Data models

Clustering algorithms

Task analysis

Symmetric matrices

Motion pictures

Multi-view clustering

multiplex network

heterogeneous graph

high-order information

multi-layer networks

Multi-View Attributed Graph Clustering

Abstract

AI Summary

Journal

Organization